基于特征优选与深度学习的车载电源微小故障诊断方法

doi:10.12382/bgxb.2021.0577

摘要/Abstract

摘要： 车载电源作为军队武器装备作训和应急的主要电能来源，其微小故障的准确诊断可有效预防严重故障的发生。然而实际监测数据往往存在冗余，且微小故障征兆难以有效提取，针对此提出一种基于递归特征消除(RFE)与栈式自编码神经网络(SAE)相结合的微小故障智能诊断方法。利用REF算法对所采集的特征变量进行重要度排序，以消除冗余并优选构建故障特征子集；再以该特征子集作为SAE深度网络的输入，微小故障类别作为输出，从而实现车载电源微小故障的有效诊断。仿真结果表明，与单纯SAE及浅层神经网络相比，所提方法的微小故障诊断准确率有明显提升，达到95.4%。

关键词: 车载电源, 微小故障诊断, 递归特征消除, 栈式自编码网络

Abstract: The vehicle power supply is the main power source for the training and emergency management of military equipment. The accurate diagnosis of incipient faults can effectively prevent the occurrence of serious faults. However, monitoring data is often redundant, making it difficult to effectively extract the symptoms of incipient faults. Aiming at this issue, a new intelligent incipient fault diagnosis method is proposed based on a combination of recursive feature elimination (RFE) and stacked auto-encoders (SAE). The collected feature variables are sorted based on their importance by using RFE to eliminate redundancy and extract the optimal subset of feature features. Then, the feature subset is used as the input of the SAE deep network, and the incipient fault category is used as the output, resulting in the effective diagnosis of incipient faults in vehicle power supply. The simulation results show that compared with SAE and shallow neural networks, the diagnosis accuracy of the proposed method is significantly improved, reaching 95.4%.

Key words: vehiclepowersupply, incipientfaultdiagnosis, recursivefeatureelimination, stackedauto-encoder

中图分类号:

李炜，韩寅龙，孙晓静. 基于特征优选与深度学习的车载电源微小故障诊断方法[J]. 兵工学报, 2022, 43(11): 2935-2944.

LI Wei, HAN Yinlong, SUN Xiaojing. Incipient Fault Diagnosis Method of Vehicle Power Supply Based on Feature Optimization and Deep Learning[J]. Acta Armamentarii, 2022, 43(11): 2935-2944.

参考文献

［1］马晓军，袁东，项宇，等.陆战平台综合电力系统及其关键技术研究［J］.兵工学报，2017，38(2):396-406.
MA X J，YUAN D，XIANG Y，et al. Research on inte-grated power system and its key techniques of ground combat platform［J］.Acta Armamentarii，2017，38(2):396-406.(in Chinese)
［2］蔡行荣，庄衍平，杨少尉.低噪声车载电站的设计与选型［J］.通信电源技术，2008，25(3):73-78.
CAI H R，ZHUANG Y P，YANG S W.Low-noise mobile power plant design and selection［J］. Telecom Power Technologies，2008, 25(3):73-78.(in Chinese)
［3］高强，廖自力，袁东，等.车载综合电力系统关键参数对系统稳定性的影响［J］.兵工学报，2020，41(9):1727-1735.(in Chinese)
GAO Q，LIAO Z L，YUAN D，et al.Effects of key parameters of integrated power system on vehicle stability［J］.Acta Armamentarii，2020，41(9):1727-1735.
(in Chinese)
［4］李娟，周东华，司小胜，等.微小故障诊断方法综述［J］.控制理论与应用，2012，29(12):1517-1529.
LI J，ZHOU D H，SI X S，et al. Review of incipient fault diagnosis methods［J］. Control Theory & Applications，2012，29(12):1517- 1529.(in Chinese)
［5］文成林，吕菲亚，包哲静，等.基于数据驱动的微小故障诊断方法综述［J］.自动化学报，2016，42(9):1285-1299.
WEN C L，L F Y，BAO Z J，et al.A review of data driven-based incipient fault diagnosis［J］.Acta Automatica Sinica，2016，42(9): 1285-1299.(in Chinese)
［6］彭开香，马亮，张凯.复杂工业过程质量相关的故障检测与诊断技术综述［J］.自动化学报，2017，43(3):349-365.
PENG K X，MA L，ZHANG K.Review of quality-related fault detection and diagnosis techniques for complex in-dustrial processes［J］.Acat Automatica Sinica，2017，43(3):349-365.(in Chinese)
［7］ BHALLA D，BANSAL R K，GUPTA H O. Function analysis based rule extraction from artificial neural networks for transformer incipient fault diagnosis［J］.International Journal of Electrical Power & Energy Systems, 2012，43(1):1196-1203.
［8］ ZHANG Z Y，WANG Y，WAMNG K S. Fault diagnosis and prog-nosis using wavelet packet decomposition Fourier transform and artificial neural network［J］.Journal of Intelligent Manufacturing，2013，24(6):1213-1227.
［9］ HINTON G E，SALAKHUTDINOV R R.Reducing the di-mensionality of data with neural networks［J］.Science，2006，313(5786): 504-507.
［10］ TAMILSELVAN P，WANG P F.Failure diagnosis using deep belief learning based health state classification［J］. Re-liability Engineering & System Safety，2013，115(jul):124-135.
［11］宫文峰，陈辉，张美玲，等.基于深度学习的电机轴承微小故障智能诊断方法［J］.仪器仪表学报，2020，41(1):195-205.
GONG W F，CHEN H，ZHANG M L，et al. Intelligent diagnosis method for incipient fault of motor bearing based on deep learning［J］.Chinese Journal of Scientific Instru-ment，2020，41(1):195- 205.(in Chinese)
［12］冒泽慧，顾彧行，姜斌，等.基于改进LSTM的高速列车牵引系统微小渐变故障诊断［J］.中国科学:信息科学，2021，51(6):997-1012.
MAO Z H，GU Y X，JIANG B，et al. Incipient fault di-agnosis for high-speed train traction systems via improved LSTM［J］.Scientia Sinica(Informationis)，2021，51(6):997-1012.(in Chinese)
［13］宫文峰，陈辉，WANG Danwei.基于深度学习的船舶机械微小故障快速诊断方法［J/OL］.计算机集成制造系统，2022, 28(9): 2852-2864.
GONG W F，CHEN H，WANG D W.Fast diagnosis method of incipient fault of marine machinery based on deep learn-ing［J］.Computer Integrated Manufacturing Systems，2022, 28(9): 2852-2864. (in Chinese)
［14］李炜，周丙相，蒋栋年.基于深度学习序贯检验的电源车故障诊断方法［J］.系统仿真学报，2020,32(4):638-648.
LI W，ZHOU B X，JIANG D N.Fault diagnosis method of vehicle power supply based on deep learning and se-quential test［J］.Journal of System Simulation，2020,32(4):638-648.(in Chinese)
［15］樊波，牛天林，薛钧义.基于MATLAB的发电机失磁故障仿真研究［J］.电气技术，2007(2):60-63.
FAN B，NIU T L，XUE J Y.The simulation research of generator loss-of-excitation faults based on MATLAB［J］.Electrical Engineering，2007(2):60-63.(in Chinese)
［16］邓国良.同步发电机失磁故障的仿真研究［J］.广东电力，2011，24(11):44-47.
DENG G L.Simulation study on fault of loss of excita-tion of synchronous generators［J］.Guangdong Electric Power，2011，24(11): 44-47.(in Chinese)
［17］钟慧荣，周云海，钟军，等.水轮发电机失磁动态过程仿真［J］.三峡大学学报(自然科学版)，2004，26(1):15-18.
ZHONG H R，ZHOU Y H，ZHONG J，et al.Simulation of dynamic processes for hydro-generator under loss of ex-citatio［J］.Journal of China Three Gorges University(Natural Sciences)，2004，26(1):15-18.(in Chinese)
［18］王琦，林治国，高海波，等.永磁同步电机失磁故障仿真研究［J］.中国修船，2019，32(4):46-49.
WANG Q，LIN Z G，GAO H B，et al.Simulation research on loss of magnetic fault of permanent magnet synchronous motor［J］.China Shiprepair，2019，32(4):46-49.(in Chinese)
［19］ BREKKEN T K A，MOHAN N.Control of a doubly fed induction wind generator under unbalanced grid voltage conditions［J］.IEEE Transactions on Energy Conversion Ec，2007，22:129-135.
［20］李俊卿，何龙，王栋.双馈式感应发电机转子匝间短路故障的负序分量分析［J］.大电机技术，2014(2):14-18.
LI J Q，HE L，WANG D.Negative sequence component of the doubly fed induction generator rotor inter-turn short circuit fault analysis［J］.Large Electric Machine and Hy-draulic Turbine，2014(2):14-18.(in Chinese)
［21］王邵然.并网运行双馈风电机组早期故障及其演化规律研究［D］.乌鲁木齐:新疆大学，2018.
WANG S R.Research on early faults and evolution laws of doubly-fed induction generator in grid-connected op-erations［D］.Urumqi:Xinjiang University，2018.(in Chinese)
［22］徐学武.康明斯柴油发电机组频率不稳故障分析及解决［J］.设备管理与维修，2012(4):19-20.
XU X W.Analysis and solution of frequency instability fault of cummins diesel generator set［J］.Plant Mainte-nance Engineering，2012(4):19-20.(in Chinese)
［23］庄智水.柴油发电机组常见故障分析及处理措施［J］. 水电站机电技术，2019，42(4):58-61.
ZHUANG Z S.Analysis and treatment measures of common faults of diesel generator set［J］.Mechanical & Electrical Technique of Hydropower Station，2019，42(4):58-61.(in Chinese)
［24］丁连生，顾明，姜耀华.柴油机常见故障与调速器的关系［J］.农机化研究，2005(6):218-220.
DING L S，GU M，JIANG Y H.The relationshi between common faults of diesel engine and the governor［J］. Journal of Agricultural Mechanization Research，2005(6):218-220.(in Chinese)
［25］卢新湘，赵东升.电子调速器故障判断与排除［J］.小型内燃机与摩托车，2009，38(3):93-96.
LU X X，ZHAO D S.Trouble judgment and removal for electronic speed-adjustor［J］.Small Internal Combustion Engine and Vehicle Technique，2009，38(3):93-96.(in Chinese)
［26］ GUYON I，WESTON J，BARNHILL S，et al.Gene selection for cancer classification using support vector machines［J］.Machine Learning，2002，46(1/2/3):389-422.
［27］ BENGIO Y.Learning deep architectures for AI［J］. Founda-tions and Trends in Machine Learning，2009， 2(1):1-127.
［28］袁非牛，章琳，史劲亭，等.自编码神经网络理论及应用综述［J］.计算机学报，2019，42(1):203-230.
YUAN F N，ZHANG L，SHI J T，et al.Theories and applications of auto-encode neural networks: a litera-ture survey［J］. Chinese Journal of Computers，2019，42(1):203-230.(in Chinese)
［29］丁石川，厉雪衣，杭俊，等.深度学习理论及其在电机故障诊断中的研究现状与展望［J］.电力系统保护与控制，2020，48(8): 172-187.
DING S C，LI X Y，HANG J，et al.Deep learning theory and its application to fault diagnosis of an electric ma-chine［J］.Power System Protection and Control，2020，48(8):172-187.(in Chinese)
［30］ BENGIO Y，LAMBLIN P，POPOVICI D，et al. Greedy layer-wise training of deep networks［J］.Advances in Neural Information Processing Systems，2007，19:153-160.